© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22375
    Prev
    Next
    INDEX
    Explanations

    authors and affiliations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĤеÑĢна
    -0.08
    kort
    -0.07
     vyh
    -0.07
    ÑĨеле
    -0.07
    profil
    -0.07
    é»Ħéĩij
    -0.07
    emn
    -0.07
    ervas
    -0.07
    kach
    -0.07
    menes
    -0.07
    POSITIVE LOGITS
    pers
    0.07
    ael
    0.07
     ÙĨس
    0.07
     pers
    0.06
    odon
    0.06
    utt
    0.06
    rows
    0.06
    {{{
    0.06
    ä¸įåı¯éģ¿åħį
    0.06
    aku
    0.06
    Activations Density 0.192%

    No Known Activations